checklist
Skill23 starsChanged 2 months agoMITView on GitHub
Use when a feature's requirements need testing for one concern before planning or building: \"make a security checklist for this spec\", \"are the UX requirements complete?\", \"review the API requirements\", \"what did the spec forget about accessibility?\", \"give me a requirements checklist for this feature\", \"does our spec cover abuse or partial failure?\", a spec that looks thin on one area such as security, access rules or error recovery, or a sensitive feature heading into `blueprint` or `build`. Not for testing code or QA steps (that's `qa`), not for checking documents against each other (that's `analyze`).
12 other projects use a version of this.
Adopted by
Most recently taken up by
- thistleknot/skillstheir own version, first seen Nov 8, 2026
- Hainrixz/claude-dbtheir own version, first seen Nov 1, 2026
- chrisbrine/checklisttheir own version, first seen Oct 25, 2026
- durchnull/rendertheir own version, first seen Oct 15, 2026
- brianharms/skill-checklisttheir own version, first seen Oct 15, 2026
- Mapsui/Mapsuitheir own version, first seen Oct 8, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- Mapsui/Mapsui★ 1.6ksame name
- unlearndev/skills★ 101same name
- ArvorCo/Relentless★ 98same name
- Hainrixz/claude-db★ 22same name
- deciqAI/knowledge-skills★ 13same name
- Huangjiacong1314520/SKILLS★ 4same name
- chrisbrine/checklist★ 1same name
- KazukiShinomiya/sdd-starter★ 1same name
- Nexus-Organization-Infosec/ClaudeSkills★ 1same name
- brianharms/skill-checklist★ 0same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- assessSkill
- blueprintSkill
- breakdownSkill
- buildSkill
- clarifySkill
- constitutionSkill
- convergeSkill
- debugSkill
- deepenSkill
- deprecateSkill
- double-checkSkill
- explainSkill
- handoffSkill
- helpSkill
- initSkill
- interviewSkill
- learnSkill
- levelupSkill
- lintSkill
- living-docsSkill
- performanceSkill
- personaSkill
- promptSkill
- prototypeSkill
- qaSkill
- quarantineSkill
- reportSkill
- roadmapSkill
- routeSkill
- signatureSkill
- specifySkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
When a model's output drives an action, the security list asks whether the spec limits that action in code.
- Distinctive: line 49
The pull toward test cases is strong: Every item that describes clicking, calling or rendering is in the wrong file.
- Distinctive: line 53
Leave it to that skill.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
MasterMind: Checklist
A checklist here is a unit test for the requirements' wording: each item asks whether the spec says enough, clearly enough, about one concern. It never asks whether the code works. Feature and concern: $ARGUMENTS.
Tests the code (wrong here): Verify the logo shows on the home page.
Tests the requirement (right): Does the spec say what is shown when the logo fails to load? [Gap, Edge cases]Write it
- Pick the concern. From the request, or the riskiest one the spec touches: security, privacy, UX, accessibility, API, data, performance, localization. Ask only if two concerns are equally likely, and recommend one.
- Read the feature's
spec.md, plusplan.mdandtasks.mdif they exist, and the constitution. - Write 10 to 30 items to
specs/<feature>/checklists/<concern>.md. Each item is a question about the requirements, ends with its quality dimension, and cites a spec ID or[Gap]:
- [ ] CHK007 Are rate limits specified for every public endpoint? [Completeness, FR-009]
- [ ] CHK008 Is "secure session" defined with an expiry and a revocation rule? [Clarity, FR-012]
- [ ] CHK009 Does the spec say who may delete another user's export? [Gap, Coverage]When a model's output drives an action, the security list asks whether the spec limits that action in code. An instruction in a prompt is not a boundary.
Quality dimensions: Completeness · Clarity · Consistency · Measurability · Coverage (edge, error, recovery, non-functional) · Assumptions · Conflicts.
Rules
- At least 80% of items cite a spec ID or
[Gap]. An item with no anchor is an opinion. - Never tick a box you generated.
[x]means a reviewer judged the requirement good enough. Mark only what the user asks you to evaluate, and say which you marked. - Append, never overwrite. A second run on the same concern adds items with new IDs.
- Items start with a question word: Are, Is, Does, Do, Can. "Verify", "Test" and "Confirm" mean you slipped into testing code.
Gotchas
- The pull toward test cases is strong. Every item that describes clicking, calling or rendering is in the wrong file. Rewrite it as a question about what the spec says.
- One concern per file. A checklist mixing security and copy-editing gets skimmed.
- The built-in
checklists/requirements.mdbelongs tospecifyand checks general spec quality. Leave it to that skill.
Report
The file path, the item count by dimension, the three gaps most likely to cause rework, and whether
they need interview before planning or building continues. Layout and paths follow
~/.mastermind/engineering/core/spec-driven.md. Then run mastermind next and end with the step it names.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

